CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

common-sdlc-metrics

Define the delivery metrics contract for agent-assisted SDLC — DORA four plus per-stage indicators derived from artifact and git history, and the control bands that turn metric drift into a routed intake. Use when reporting cycle time, plan adherence, or defining response thresholds.

68

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, well-structured contract: prescriptive rules with concrete definitions, paths, and thresholds; clean one-level-deep references to a real schema and template; and no filler. Remaining gaps are minor — a couple of per-stage indicators lack derivation formulas, and the reporting sequence is implied by section order rather than explicit steps.

Suggestions

Add one-line derivation rules (or point to where they live) for table indicators named without formulas, e.g. 'defect escape rate' and 'eval pass rate'.

State the reporting sequence explicitly (gather raw counts → derive indicators → apply bands → emit artifacts/sdlc-metrics.md) instead of leaving the order implicit across sections 1–5.

DimensionReasoningScore

Conciseness

The body is lean and directive throughout: 'Measure the handoffs, not the keystrokes', 'unavailable inputs are reported as unavailable, never estimated', 'No composite scores: do not blend indicators into a single productivity number'. It never explains what DORA or git is, assumes Claude's competence, and every section prescribes rather than pads.

5 / 5

Actionability

Guidance is concrete and executable for an instruction-only skill: exact metric definitions ('Change failure rate: deploys needing hotfix or rollback, divided by deploys'), concrete paths ('docs/ops/bands.yaml', 'artifacts/sdlc-metrics.md'), and a per-stage indicator table. Not anchor 5 because a few table indicators such as 'defect escape rate' and 'eval pass rate' are named without a derivation rule in either the body or the schema reference.

4 / 5

Workflow Clarity

The reporting workflow is well structured — emit at 'a workflow terminal state, alongside artifacts/session-cost.md', 'Load references/metrics-schema.md for the report skeleton', band 'Detection is deterministic and computed before any agent reads the signal' — with report-time checkpoints (cite source, mark unavailable, trend vs previous). Not anchor 5 because the gather → derive → emit sequence is implicit in sections rather than stated as an ordered procedure.

4 / 5

Progressive Disclosure

The body is an overview contract that delegates detail at the right depth: 'Load references/metrics-schema.md for the report skeleton' and 'Schema: references/bands-template.yaml', both real files in the bundle, confirmed one level deep with no further nested references, plus a clean References section. Content is appropriately split between the contract body, the report skeleton, and the bands template.

5 / 5

Total

18

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description in third person with an explicit 'Use when' clause, concrete capability statements, and domain-specific trigger terms. Its only weaknesses are minor: a few natural keyword variants live in metadata rather than the description, and 'cycle time'/'response thresholds' are slightly generic.

Suggestions

Fold one or two high-frequency variants from the metadata triggers (e.g., 'lead time', 'change failure rate') into the description's 'Use when' clause so the terms users actually say appear in the description itself.

Tighten the 'when' clause with a qualifier like 'delivery/SDLC cycle time' to reduce overlap with generic CI or observability metrics skills.

DimensionReasoningScore

Specificity

The description names several concrete capabilities — 'Define the delivery metrics contract', 'DORA four plus per-stage indicators derived from artifact and git history', 'the control bands that turn metric drift into a routed intake' — rather than vague language. It stops short of anchor 5 because emission of the report artifact and unavailable-input handling are covered only in the body, leaving minor coverage gaps.

4 / 5

Completeness

It explicitly answers both parts: 'Define the delivery metrics contract for agent-assisted SDLC — DORA four plus per-stage indicators... and the control bands...' (what) and 'Use when reporting cycle time, plan adherence, or defining response thresholds' (when, with concrete trigger phrases). This matches the anchor-5 good example's structure exactly.

5 / 5

Trigger Term Quality

It carries good natural terms a user would say: 'delivery metrics', 'cycle time', 'plan adherence', 'response thresholds', 'DORA'. Not anchor 5 because common variations users might say — 'lead time', 'change failure rate' — appear only in the frontmatter metadata triggers, not the description itself.

4 / 5

Distinctiveness Conflict Risk

The niche is clear — agent-assisted SDLC delivery metrics with DORA and control bands — with triggers specific to that domain. Not anchor 5 because terms like 'cycle time' and 'response thresholds' have minor overlap risk with generic observability or CI-metrics skills.

4 / 5

Total

17

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

HoangNguyen0403/agent-skills-standard

Path

.agents/skills/common/common-sdlc-metrics/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.